I have yet another Meetup talk to announce:
On Wednesday, September 26th, I’ll be talking about ‘Decoding The Black Box’ at the Frankfurt Data Science Meetup.
Particularly cool with this meetup is that they will livestream the event at www.youtube.com/c/FrankfurtDataScience!
TALK#2: DECODING THE BLACK BOX
And finally we will have with us Dr.Shirin Glander, whom we were inviting for a long time back. Shirin lives in Münster and works as a Data Scientist at codecentric, she has lots of practical experience.

Today I am very happy to announce that during my stay in London for the m3 conference, I’ll also be giving a talk at the R-Ladies London Meetup on Tuesday, October 16th, about one of my favorite topics: Interpretable Deep Learning with R, Keras and LIME.
You can register via Eventbrite: https://www.eventbrite.co.uk/e/interpretable-deep-learning-with-r-lime-and-keras-tickets-50118369392
ABOUT THE TALK
Keras is a high-level open-source deep learning framework that by default works on top of TensorFlow.

In our next MünsteR R-user group meetup on Tuesday, August 28th, 2018 Jenny Saatkamp will give a talk titled Blog Mining: Deriving the success of blog posts from metadata and text data. You can RSVP here: http://meetu.ps/e/F7zDN/w54bW/f
In our next MünsteR Meetup, Jenny Saatkamp will present her Blog Mining analysis, which is based on 1.500 blog posts from the codecentric company blog (https://blog.codecentric.de/) and makes use of different mining techniques for metadata and text data.

In our next MünsteR R-user group meetup on Monday, June 11th, 2018 Thomas Kluth and Thorben Jensen will give a talk titled Look, something shiny: How to use R Shiny to make Münster traffic data accessible. You can RSVP here: http://meetu.ps/e/F7zDN/w54bW/f
About a year ago, we stumbled upon rich datasets on traffic dynamics of Münster: count data of bikes, cars, and bus passengers of high resolution. Since that day we have been crunching, modeling, and visualizing it.

On April 12th, 2018 I gave a talk about Explaining complex machine learning models with LIME at the Hamburg Data Science Meetup - so if you’re intersted: the slides can be found here: https://www.slideshare.net/ShirinGlander/hh-data-science-meetup-explaining-complex-machine-learning-models-with-lime-94218890
Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria.

On April 4th, 2018 I gave a talk about Deep Learning with Keras at the Ruhr.Py Meetup in Essen, Germany. The talk was not specific to Python, though - so if you’re intersted: the slides can be found here: https://www.slideshare.net/ShirinGlander/ruhrpy-introducing-deep-learning-with-keras-and-python
Ruhr.PY - Introducing Deep Learning with Keras and Python von Shirin Glander There is also a video recording of my talk, which you can see here: https://youtu.

In our next MünsteR R-user group meetup on Tuesday, April 17th, 2018 Kai Lichtenberg will talk about deep learning with Keras. You can RSVP here: http://meetu.ps/e/DDY1B/w54bW/f
Although neural networks have been around for quite a while now, deep learning really just took of a few years ago. It pretty much all started when Alex Krizhevsky and Geoffrey Hinton utterly crushed classic image recognition in the 2012 ImageNet Large Scale Visual Recognition Challenge by implementing a deep neural network with CUDA on graphics cards.